Skip to content
AI News HubLIVE
Original source2 min read

GOPAgen: Motion-Aware and Efficient Agentic Long-Video Understanding with Structural Memory and Hierarchical Reasoning

Summary

GOPAgen introduces a motion-aware agentic framework that integrates video codec Groups of Pictures, GOP-tree reasoning, structural memory with coarse-to-fine zoom-in, and a multi-granularity motion vector database, achieving superior VQA performance on MotionBench and Egoschema.

SourcearXiv Computer VisionAuthor: Haozhe Chi, Yang Jin, Yadong Mu
GOPAgen: Motion-Aware and Efficient Agentic Long-Video Understanding with Structural Memory and Hierarchical Reasoning
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.06532] GOPAgen: Motion-Aware and Efficient Agentic Long-Video Understanding with Structural Memory and Hierarchical Reasoning

[Submitted on 3 Jun 2026]

Title:GOPAgen: Motion-Aware and Efficient Agentic Long-Video Understanding with Structural Memory and Hierarchical Reasoning

View a PDF of the paper titled GOPAgen: Motion-Aware and Efficient Agentic Long-Video Understanding with Structural Memory and Hierarchical Reasoning, by Haozhe Chi and 2 other authors

View PDF HTML (experimental)

Abstract:Despite significant progress in agentic long video understanding, existing methods still lack detailed motion comprehension coupled with an efficient memory architecture. In this paper, we propose GOPAgen, a novel approach that first integrates video codec into the video understanding framework via a meticulously designed motion agent trained on Groups of Pictures (GOPs) from video codec. We further develop a GOP tree reasoning algorithm, which is naturally aligned with video codec and enhances the model's ability to understand local detailed motions in videos. Additionally, we carefully design a structural memory mechanism that integrates local motion information with detailed captions in structural pages, and propose an efficient coarse-to-fine zoom-in algorithm to fully exploit the structural memory. Furthermore, we incorporate a motion vector database into the framework to enable efficient retrieval of motion vectors at different granularities. Overall, our method achieves superior Video Question Answering (VQA) performance on various video understanding benchmarks, including MotionBench and Egoschema, thereby demonstrating the superiority of our proposed framework.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2606.06532 [cs.CV]

(or arXiv:2606.06532v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2606.06532

arXiv-issued DOI via DataCite

Submission history

From: Haozhe Chi [view email] [v1] Wed, 3 Jun 2026 17:47:49 UTC (1,070 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled GOPAgen: Motion-Aware and Efficient Agentic Long-Video Understanding with Structural Memory and Hierarchical Reasoning, by Haozhe Chi and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • A motion agent trained on codec GOPs brings fine-grained motion cues into long-video understanding.
  • A GOP-tree reasoning algorithm and structural memory pages enable efficient coarse-to-fine hierarchical retrieval.
  • A motion vector database supports multi-granularity retrieval, with strong VQA results on MotionBench and Egoschema.

Highlights and analysis are generated automatically and may contain errors. Check the original source.